CN105224992A - To waiting for the method and system predicted of ridership and evaluation method and system - Google Patents
To waiting for the method and system predicted of ridership and evaluation method and system Download PDFInfo
- Publication number
- CN105224992A CN105224992A CN201410229206.1A CN201410229206A CN105224992A CN 105224992 A CN105224992 A CN 105224992A CN 201410229206 A CN201410229206 A CN 201410229206A CN 105224992 A CN105224992 A CN 105224992A
- Authority
- CN
- China
- Prior art keywords
- motorbus
- ridership
- station
- prediction
- history
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Finance (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to waiting for the method and system predicted of ridership and evaluation method and system.Providing a kind of for waiting for the method predicted of ridership, comprising: based on the history running data of motorbus and Current vehicle service data, the arrival time that motorbus arrives a station is predicted; And based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, the waiting Passengen number of described station subsequent period is predicted.
Description
Technical field
The present invention relates to bus scheduling, more specifically, relating to a kind of for waiting for the method and system predicted of ridership and evaluation method and system, and a kind of evaluation method of the scheduling scheme for motorbus and evaluation system.
Background technology
On-line scheduling plays an important role in motorbus operation system, cannot adapt because dispatch (static scheduling) based on the off-line of predefined demand with various dynamic change.On-line scheduling comprises such as motorbus departures board scheduling, the speed of a motor vehicle controls, jump station instruction etc.Usually, dispatching the state only based on the state of motorbus or the motorbus of prediction, not considering passenger flows information when dispatching motorbus.Because do not know the boarding time, so bus status cannot be predicted exactly
Such as, when because the ridership at last station than usual many a lot of thus cause step on the car time long time, this motorbus arrives the actual arrival time of the next stop may be more late than the arrival time of prediction.In another example, public transport bunching (Busbunching) problem is discussed.Fig. 2 shows the key diagram explaining public transport bunching problem.In fig. 2, triangle represents motorbus, and they are scheduled as and should travel substantially equally spacedly, and at least two motorbuses of same public bus network travel together and are called as public transport bunching.Public transport bunching makes service unreliable, and such as, the stand-by period of some passengers can be longer, and some motorbuses can be crowded.Fig. 3 shows the key diagram of passenger flows situation when there is public transport bunching.In figure 3, the length of rectangular strip corresponds to the berthing time of motorbus.The curve map of Fig. 3 lower right side shows the passenger flows situation at first station under normal circumstances, and the curve map of Fig. 3 upper right side shows the passenger flows situation at the 3rd station when there is public transport bunching.A key reason of public transport bunching is abnormal passenger load, increases the berthing time of motorbus because step on car passengers quantity senior general thus causes delay.Sometimes, public transport bunching is not harmful.Such as, when certain large-scale exhibition or sports tournament end of a performance, nigh station there will be abnormal passengers quantity lifting, now in order to the passenger flows of satisfied burst, expects the appearance of public transport bunching on the contrary.
Therefore, not only based on bus status, the public transit system of passenger services should also should be scheduling to based on passenger flows information.This just relates to the prediction of passenger flows.
In the prior art performing passenger flows prediction, there is non-parametric statistical method, parametric approach and real-time emulation method.
Non-parametric statistical method comprises such as neural network, SVM (support vector machine) etc.Non-parametric statistical method require such as date, time and weather environmental variance as input variable, and try to achieve the relation between passenger flows and environmental baseline.But the position strong correlation of waiting Passengen number motorbus, so be difficult to be modeled as environmental baseline.
Parametric approach such as comprises linear regression, temporal model, Kalman filtering etc.Some predictions 1 year in these technology or the passenger flows in time interval of N days, this prediction is carried out for timely decision-making too coarse for bus scheduling person.In Kalman filtering, WPC (t+1)=WPC (t)+w (t), wherein WPC () represents waiting Passengen number, w () represents Gaussian noise, does not consider the position of passenger demand and motorbus as seen in this passenger flows prediction.
Real-time emulation method is estimated based on real-time OD (starting point-destination).Real-time emulation method requires that emulation supported by mass data (such as, history OD matrix) and efficient computing machine, and this is high cost for bus scheduling.
Summary of the invention
Consider above problem, the present invention aims to provide and a kind ofly bus location is predicted predict with passenger flows the method and system be combined with each other, and a kind of evaluation method of the scheduling scheme for motorbus and evaluation system.
According to an aspect of the present invention, providing a kind of for waiting for the method predicted of ridership, comprising: based on the history running data of motorbus and Current vehicle service data, the arrival time that motorbus arrives a station is predicted; And based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, the waiting Passengen number of described station subsequent period is predicted.
According to another aspect of the present invention, provide a kind of evaluation method of the scheduling scheme for motorbus, comprising: based on the history running data of motorbus and Current vehicle service data, the arrival time that motorbus arrives a station is predicted; Based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, the waiting Passengen number of described station subsequent period is predicted; Using prediction waiting Passengen number and the integration of their stand-by period as KPI Key Performance Indicator KPI; And the scheduling scheme of motorbus is evaluated, to determine whether described KPI Key Performance Indicator KPI is less than predetermined value.
According to another aspect of the present invention, provide a kind of system for predicting wait ridership, comprise: arrival time fallout predictor, be configured to predict the arrival time that motorbus arrives a station based on the history running data of motorbus and Current vehicle service data; And waiting Passengen number fallout predictor, be configured to based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, the waiting Passengen number of described station subsequent period predicted.
According to another aspect of the present invention, provide a kind of evaluation system of the scheduling scheme for motorbus, comprise: arrival time fallout predictor, be configured to predict the arrival time that motorbus arrives a station based on the history running data of motorbus and Current vehicle service data; Waiting Passengen number fallout predictor, is configured based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, predicts the waiting Passengen number of described station subsequent period; KPI Key Performance Indicator KPI arranges device, be configured to using prediction waiting Passengen number and the integration of their stand-by period as KPI; And evaluator, be configured to evaluate the scheduling scheme of motorbus, to determine whether described KPI Key Performance Indicator KPI is less than predetermined value.
The waiting Passengen number that method and system according to the present invention is predicted and actual waiting Passengen number are more close and substantially identical.In addition, the waiting Passengen number adopting method and system according to the present invention to predict carrys out the KPI of installation surface to passenger, can reflect the overall experience of passenger to the service of public transit system more realistically.In addition, utilize the scheduling scheme of described KPI to motorbus to evaluate, and find out the scheduling scheme meeting this KPI based on this evaluation, the satisfaction of passenger to the service of public transit system can be improved.
Accompanying drawing explanation
In conjunction with the drawings disclosure illustrative embodiments is described in more detail, above-mentioned and other object of the present disclosure, Characteristics and advantages will become more obvious, wherein, in disclosure illustrative embodiments, identical reference number represents same parts usually.
Fig. 1 shows the block diagram of the exemplary computer system/server 12 be suitable for for realizing embodiment of the present invention.
Fig. 2 shows the key diagram explaining public transport bunching problem.
Fig. 3 shows the key diagram of passenger flows situation when there is public transport bunching.
Fig. 4 illustrates according to an embodiment of the invention for waiting for the process flow diagram of method that ridership is predicted.
Fig. 5 shows the example of the running time of the stretch journey of prediction.
Fig. 6 shows the process flow diagram of the process in waiting Passengen number prediction steps according to an embodiment of the invention.
Fig. 7 illustrates according to an embodiment of the inventionly to obtain from the car ridership of stepping on history passenger flow data the diagram arriving ridership APC.
Fig. 8 illustrates to utilize seasonal ARIMA model to predict the diagram of the example of APC.
Fig. 9 shows the process flow diagram that the process in the step of car ridership DPC is stepped in prediction according to an embodiment of the invention.
Figure 10 shows the KPI Key Performance Indicator KPI that utilization is arranged according to the waiting Passengen number of embodiments of the invention prediction.
Figure 11 illustrates according to an embodiment of the invention for the process flow diagram of the evaluation method of the scheduling scheme of motorbus.
Figure 12 shows the effect of the prediction according to waiting Passengen number of the present invention.
Figure 13 illustrates according to an embodiment of the invention for waiting for the block scheme of system that ridership is predicted.
Figure 14 illustrates according to an embodiment of the invention for the block scheme of the evaluation system of the scheduling scheme of motorbus.
Embodiment
Below with reference to accompanying drawings preferred implementation of the present disclosure is described in more detail.Although show preferred implementation of the present disclosure in accompanying drawing, but should be appreciated that, the disclosure can be realized in a variety of manners and not should limit by the embodiment of setting forth here.On the contrary, provide these embodiments to be to make the disclosure more thorough and complete, and the scope of the present disclosure intactly can be conveyed to those skilled in the art.
Fig. 1 shows the block diagram of the exemplary computer system/server 12 be suitable for for realizing embodiment of the present invention.The computer system/server 12 of Fig. 1 display is only an example, should not bring any restriction to the function of the embodiment of the present invention and usable range.
As shown in Figure 1, computer system/server 12 shows with the form of universal computing device.The assembly of computer system/server 12 can include but not limited to: one or more processor or processing unit 16, system storage 28, connects the bus 18 of different system assembly (comprising system storage 28 and processing unit 16).
Bus 18 represent in a few class bus structure one or more, comprise memory bus or Memory Controller, peripheral bus, AGP, processor or use any bus-structured local bus in multiple bus structure.For example, these architectures include but not limited to industry standard architecture (ISA) bus, MCA (MAC) bus, enhancement mode isa bus, VESA's (VESA) local bus and periphery component interconnection (PCI) bus.
Computer system/server 12 typically comprises various computing systems computer-readable recording medium.These media can be any usable mediums can accessed by computer system/server 12, comprise volatibility and non-volatile media, moveable and immovable medium.
System storage 28 can comprise the computer system-readable medium of volatile memory form, such as random access memory (RAM) 30 and/or cache memory 32.Computer system/server 12 may further include that other is removable/immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 may be used for reading and writing immovable, non-volatile magnetic media (Fig. 1 does not show, and is commonly referred to " hard disk drive ").Although not shown in Fig. 1, the disc driver that removable non-volatile magnetic disk (such as " floppy disk ") is read and write can be provided for, and to the CD drive that removable anonvolatile optical disk (such as CD-ROM, DVD-ROM or other light medium) is read and write.In these cases, each driver can be connected with bus 18 by one or more data media interfaces.Storer 28 can comprise at least one program product, and this program product has one group of (such as at least one) program module, and these program modules are configured to the function performing various embodiments of the present invention.
There is the program/utility 40 of one group of (at least one) program module 42, can be stored in such as storer 28, such program module 42 comprises---but being not limited to---operating system, one or more application program, other program module and routine data, may comprise the realization of network environment in each or certain combination in these examples.Function in program module 42 embodiment that execution is described in the invention usually and/or method.
Computer system/server 12 also can communicate with one or more external unit 14 (such as keyboard, sensing equipment, display 24 etc.), also can make with one or more devices communicating that user can be mutual with this computer system/server 12, and/or communicate with any equipment (such as network interface card, modulator-demodular unit etc.) making this computer system/server 12 can carry out communicating with other computing equipment one or more.This communication can be passed through I/O (I/O) interface 22 and carry out.Further, computer system/server 12 can also such as, be communicated by network adapter 20 and one or more network (such as LAN (Local Area Network) (LAN), wide area network (WAN) and/or public network, the Internet).As shown in the figure, network adapter 20 is by bus 18 other module communication with computer system/server 12.Be understood that, although not shown, other hardware and/or software module can be used in conjunction with computer system/server 12, include but not limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system etc.
Referring now to Fig. 4, Fig. 4, be illustrate according to an embodiment of the invention for waiting for the process flow diagram of method 400 that ridership is predicted.The method 400 comprises arrive at a station time prediction step 410 and waiting Passengen number prediction steps 420.
In arrival time prediction steps 410, based on the history running data of motorbus and Current vehicle service data, the arrival time that motorbus arrives a station is predicted.Here, history running data comprises at least one in the speed of the motorbus corresponding to different time in one day in history, position, and Current vehicle service data comprises at least one in the current speed of motorbus, position.In addition, described motorbus refers to the motorbus of same public bus network.Current vehicle service data such as can be obtained by GPS, or is obtained by other sensors (such as gyroscope or RFID etc.) installed on a bus.
In one embodiment of the invention, in step 410, first, based on the history running data (such as the speed of a motor vehicle) of motorbus, history running data is used to train speed of a motor vehicle model by methods such as statistics or data minings, then based on Current vehicle service data, by filtering method, (such as, Kalman filtering (KalmanFilter) reduces the error of the speed of a motor vehicle predicted.
Then, based on the speed of a motor vehicle of the future time period (such as 15 minutes, half an hour etc.) of prediction, the prediction running time of stretch journey is obtained.Fig. 5 shows the example of the running time of the stretch journey of prediction.In Figure 5, the left side different time shown in one day weekend of Fig. 5 has started the time that this section of distance will spend, and the right side different time shown in a day on ordinary days of Fig. 5 has started the time that this section of distance will spend.In Figure 5, the line that solid dot couples together is represented the running time of observation, the line that hollow dots couples together is represented the running time of prediction.As can be seen from Fig. 5, the prediction running time of morning peak period is on ordinary days the longest.
Then, by the running time of usage forecastings and the current location of motorbus, the arrival time of motorbus can be predicted.Such as, the current location of known motorbus and drive to the prediction running time at next station from current location, easily can draw the arrival time of prediction.
Be shore, Yang Zhongzhen, Zeng Qingcheng " the bus arrival time forecast model based on SVM and Kalman filter " (" Chinese Highway journal " the 2nd phase 89-92 page in 2008) in describe a kind of bus arrival time forecast model in detail.
Then, process proceeds to waiting Passengen number prediction steps 420, at step 420 which, based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, the waiting Passengen number of described station subsequent period is predicted.
Fig. 6 shows the process flow diagram of the process 600 in waiting Passengen number prediction steps according to an embodiment of the invention.In this embodiment, waiting Passengen number prediction steps comprises: for a station, based on history passenger flow data, carries out the prediction (step 610) arriving ridership APC (ArrivalPassengerCount); Based on history passenger flow data, carry out the prediction (step 620) of the vacant seat number ESC (EmptySeatCount) of motorbus; Based on the predicting the outcome of described arrival time, predicting the outcome of described arrival ridership APC and predicting the outcome of described vacant seat number ESC, carry out the prediction (step 630) of stepping on car ridership DPC (DeparturePassengerCount); And based on described arrival ridership APC, described in step on car ridership DPC and current waiting Passengen number, predict the waiting Passengen number WPC (WaitingPassengerCount) (step 640) of described station subsequent period.
Here, history passenger flow data comprise each station correspond in history different time in one day step in the vacant seat number of car ridership and motorbus at least one, and current waiting Passengen number is taken by the video camera at described station and identifies.In one embodiment of the invention, utilize and be arranged on camera or the video camera of platform, by mode identification technology, everyone class object in the defined area of platform or platform is counted, the current waiting Passengen number at this station can be obtained.In one embodiment of the invention, the country of standing on a bus for not allowing passenger, described vacant seat number is the number of the actual vacant place on car.In another embodiment, for the country allowing passenger to stand on a bus, described vacant seat number can be the number of the passenger that the motorbus of situation estimation in the car according to shooting can also hold.In one embodiment of the invention, what history passenger flow data comprised step on, and car ridership can be obtained by the automatic passenger counting device installed on a bus, or is obtained by the shooting of installing video camera on a bus and identification.
Successively perform although the step 610 in Fig. 6 and 620 is shown as, it should be appreciated by those skilled in the art that step 610 and 620 execution sequence can put upside down or executed in parallel.Specifically describe the process of each step in the process flow diagram of Fig. 6 below.
In step 610, for a station (such as, station X), for each period (such as but not limited to 5-15 minute), obtain arrival ridership APC from the car ridership of stepping on history passenger flow data.In one embodiment of the invention, in the prediction arriving ridership, the passenger climbing up same motorbus at same station is assumed to be it is arrive this station according to specific distribution and the arriving at a station corresponding to a distribution of each motorbus, and the arrival ridership in the period equals the integration sum that is distributed in described in each in this period.
Fig. 7 illustrates according to an embodiment of the inventionly to obtain from the car ridership of stepping on history passenger flow data the diagram arriving ridership APC.Figure 7 illustrates motorbus respectively at moment τ
1, τ
2, τ
3get to the station X, thus motorbus arrival event BAE1, BAE2 and BAE3 occur.The length that car ridership corresponds respectively to the rectangle below transverse axis is stepped in event BAE1, BAE2 and BAE3.The passenger stepping on car in event BAE1 is assumed to be it is according to specific distribution (such as, Poisson distribution) X that gets to the station, this distribution correspond to above transverse axis with BAE1 event step on the shape that car ridership rectangle has same pattern (dot pattern).Similarly, the arrival of stepping on the passenger of car in BAE2 event, corresponding to the distribution shape with grid pattern, steps on the arrival of the passenger of car corresponding to the distribution shape with twill pattern in BAE3 event.
For the concern period (t-1 in Fig. 7, t), the distribution (corresponding to BAE2) that the arrival ridership APC within this period equals to have grid pattern and the distribution (corresponding to BAE3) with twill pattern drop on the area sum of the part in this period.Formula below can be used to calculate and to arrive ridership APC:
Wherein, APC (t) represents the ridership that (t-1, t) period gets to the station, B
his(τ
i) represent i-th bus step on car ridership, τ
irepresent the arrival time of i-th bus, f (x) represents the probability density function of the ridership that arrives at a station,
represent and step on car and the ridership got to the station in (t-1, t) period at i-th bus.Mode according to above-described embodiment calculates APC, and APC can be made closer to real APC.
In another embodiment, can adopt alternatively from B
his(τ
i) draw APC (t).Such as, for every two adjacent motorbus i-1 and i arrived at a station, suppose that the arrival time of bus i-1 is τ
i-1, the arrival time of bus i is τ
iand stepping on car ridership is B
his(τ
i), so can calculate period (τ
i-1, τ
i) in the arrival ridership of unit interval be
In the case, if want computational length to be the arrival ridership of the period of T, then first check this period drops between the arrival time of which two bus.Suppose that this period drops on the arrival time u of two motorbuses in front and back
i-1and u
ibetween, then the number of arriving at a station of this period is APC (t)=TA (u
i-1, u
i).Except above embodiment, those skilled in the art it will also be appreciated that other from B
his(τ
i) draw the method for APC (t).
After obtaining arriving ridership APC, seasonal time series (ARIMA) model is used to carry out modeling to predict the APC on the same day to history APC.Seasonal ARIMA model is the modeling method for there being the time series of seasonal variation to propose.It is analyzed the sequential value of same time point in each seasonal cycle, extracts trend in season, and for the change detection Out of season composition of each seasonal cycle internal sequence value, establishes optimization model.Shown by GeogeE.P.Box, in " Time Series Analysis Forecasting and control " (China Statistics Press, the 1997,101st – 135 pages) that Gu Lanzhu translates, describing seasonal ARIMA model.At seasonal ARIMA model in an application of the invention, by analysis of history data (namely, as above the APC drawn), by the passenger flow data makeup time sequence of points of same period of many days in history, extract trend in season, seasonal ARIMA model is utilized to complete the analysis of APC data pattern, and the APC of prediction following some day same period.
Fig. 8 illustrates to utilize seasonal ARIMA model to predict the diagram of the example of APC.The top of Fig. 8 shows the arrival ridership APC historical data on bimestrial time span of station X within 5 minute period of [8:30,8:35].The bottom of Fig. 8 shows the APC on the same day utilizing seasonal ARIMA model prediction, and wherein the data of [8:30,8:35] dope based on the historical data on the top of Fig. 8.This completes the prediction arriving ridership APC.
In step 620, for a station (such as, station X), based on history passenger flow data, the prediction of the vacant seat number ESC of motorbus is carried out.Because history passenger flow data directly comprises the vacant seat number ESC (these data can be the camera acquisitions by installing on a bus) corresponding to the motorbus of the different time in a day in history at each station, so need not need to calculate from history passenger flow data as arrival ridership APC.Similar with arrival ridership APC, seasonal ARIMA model can be used to carry out modeling to predict the ESC on the same day to history ESC.By the prediction of the vacant seat number of motorbus, the ESC (not shown) on the same day of the seasonal ARIMA model prediction of the utilization shown in bottom be similar in same 8 can be obtained.This completes the prediction of the vacant seat number ESC of motorbus.
In the above example, although the prediction arriving the prediction of ridership APC and the vacant seat number ESC of motorbus utilizes Seasonal Time Series Methods to perform, but it may occur to persons skilled in the art that and utilize other statistical method or data digging method to carry out founding mathematical models, thus carry out described prediction.
In act 630, based on the predicting the outcome of described arrival time, predicting the outcome of described arrival ridership APC and predicting the outcome of described vacant seat number ESC, the prediction of stepping on car ridership DPC is carried out.Fig. 9 shows the process flow diagram that the process 900 in the step of car ridership DPC is stepped in prediction according to an embodiment of the invention.Describe an example of the process in step 630 below with reference to Fig. 9, in this example embodiment, such as, predict the DPC at period time period (t-1, t) station X.
First, in step 910, based on the arrival time of prediction in above-mentioned step 410, produce motorbus arrival event (BAE) list, in BAE list, each BAE is (a b, s) right, wherein b represents the ID of motorbus, and s represents the prediction arrival time of this motorbus.Each BAE in BAE list meets: moment (t-1) < moment s< moment t.
In step 920, from BAE list, extract a BAE successively, and perform the process of step 930 to step 970 for the BAE extracted.Assuming that the BAE proposed in this step is (BUS3, s).
In step 930, calculate ridership A=(moment s-moment (t-1))/(moment t-moment (t-1)) × APC (t) of the X that gets to the station within the period (t-1, t) and before the arrival time s of BUS3.Here, (moment s-moment (t-1)) represents from moment t-1 to the duration of moment s, (moment t-moment (t-1)) represents period (t-1, t) length, and APC (t) represents the ridership that arrives at a station at whole period (t-1, t) period station X predicted in step 610.
In step 940, calculate the waiting Passengen number W=W+A before visitor on motorbus BUS3.Here, W is a variable, and "=" represents assignment.In one embodiment of the invention, before being added with A, the value of variable W can be 0, corresponds to the situation that (t-1, t) period is start periods; Or can be the waiting Passengen number at the end of a upper period (t-2, t-1) of prediction, correspond to the situation that (t-1, t) period is not start periods.In another embodiment, before being added with A, the value of variable W can be the station X that taken by the video camera of the platform waiting Passengen number in the t-1 moment.
In step s 950, calculate climb up motorbus BUS3 step on car ridership B=min (W, ESC (t)).Here, min () represents the smaller value got in both, and ESC (t) represents the motorbus vacant seat number in period period (t-1, t) corresponding to station X predicted in step 620.That is, when current waiting Passengen number is greater than vacant seat number (W>ESC (t)), portion waits passenger is only had to step on car.
In step 960, waiting Passengen number W=W-B is upgraded.The value of the variable W after renewal represents that motorbus BUS3 leaves the residue waiting Passengen number of rear station X.Here, "=" represents assignment.Variable W after being updated can be used for for stepping on waiting Passengen number before car in next BAE calculation procedure 940.
In step 970, judge that whether current BAE is last BAE in BAE list.If not last BAE, then process turns back to step 920, extracts next BAE and performs the operation of step 930 to step 970 for this BAE.If last BAE, then process proceeds to step 980.
In step 980, the car ridership B that steps on that will calculate in step s 950 in each circulation (once circulating for each BAE) is added, thus obtain prediction step on car ridership DPC (t).That is, DPC (t) equal the period (t-1, t) period AT STATION X climb up the number summation of the passenger of each motorbus.
Thus, the prediction of stepping on car ridership DPC is completed.
Those skilled in the art are visible, and the prediction of DPC is based on motorbus arrival event BAE.That is, in the present invention, in passenger flows prediction, consider the prediction of arrival time, that is, combine bus location prediction.
According to another embodiment of the invention, step 620 can be omitted from the waiting Passengen number prediction processing shown in Fig. 6, that is, not carry out the prediction of the vacant seat number ESC of motorbus.Correspondingly, in act 630, only based on the predicting the outcome of described arrival time, the predicting the outcome of described arrival ridership APC, the prediction of stepping on car ridership DPC is carried out.Step in the prediction of car ridership DPC at such, the process shown in Fig. 9 can be adopted equally.Difference is, in step s 950, calculate climb up motorbus step on car ridership B=W (that is, not considering the vacant seat number ESC of motorbus).Further, in step 960, waiting Passengen number W=W-B=0 is upgraded.Other step is identical with the step shown in Fig. 9.Thus, the prediction of stepping on car ridership DPC can be completed equally.That is, this embodiment provides for the simplify processes of the waiting Passengen number prediction shown in a kind of Fig. 6.
In one embodiment of the invention, process 600 as shown in Figure 6 according to the present invention can also comprise: the car ridership of stepping on based on prediction calculates and steps on the car time, and according to stepping on car time complexity curve motorbus and arrive the arrival time at next station.Step on car ridership due to what such as can dope bus BUS3 in the step 950 of Fig. 9, can easily obtain stepping on car time (that is, berthing time) DTime=B × a, wherein a represents that a passenger's steps on the car time, and a is constant.By providing the berthing time DTime of BUS3 X AT STATION, the BUS3 that can revise prediction in the step 410 of Fig. 4 arrives the arrival time of the next stop.Such as, if cause the value of DTime to be greater than general value due to the car passenger that steps on of station X, then get to the station time of X+1 of the BUS3 predicted is corrected for and postpones the amount corresponding with DTime more.Therefore, in the present invention, in one embodiment of the invention, in bus location prediction, combine passenger flows prediction too, thus make predicted value closer to actual value.
Below referring back to Fig. 6.In step 640, based on described arrival ridership APC, described in step on car ridership DPC and current waiting Passengen number, predict the waiting Passengen number WPC of described station subsequent period.
According to one embodiment of present invention, utilize Kalman filtering to predict the waiting Passengen number WPC of described station subsequent period.The details of Kalman filtering is specifically described in " ANewApproachtoLinearFilteringandPredictionProblems " (TransactionsoftheASME-JournalofBasicEngineeringVol.82:pp .35-45 (1960)) of Kalman, R.E.Kalman filtering is a kind of high efficiency regressive filter (autoregressive filter), it can from a series of not exclusively and comprise the measurement of noise, estimate the state of dynamic system.The operation of Kalman filter comprises two stages: forecast period and more new stage.At forecast period, wave filter uses the estimation of laststate, makes the estimation to current state.In more new stage, wave filter utilizes the predicted value obtained at forecast period the observed reading optimization of current state, to obtain a more accurate new estimation value, also upgrades intrasystem Error Gain item simultaneously.
In step 640, the Evolution Equation in Kalman filtering is set to:
WPC(t)＝WPC(t-1)+u(t)+ω(t-1)
Wherein, u (t)=APC (t)-DPC (t) is that the state of WPC changes equation, ω (t-1) is the systematic error that state changes equation, and label t-1 and t represented the item corresponding to a upper period and present period respectively.
Then, the observation equation in Kalman filtering is set to:
y(t)＝WPC(t)+υ(t-1)
Wherein, y (t) is the observed reading of WPC, and υ (t-1) is the error of the WPC of observation.
Particularly, at forecast period, the WPC (that is, WPC (t-1)) of a period and state is used to change equation u (t)=APC (t)-DPC (t), estimate the WPC (that is, WPC (t)) of present period.In more new stage, use the WPC observed reading (take by the camera at station and identify, be i.e. y (t)) of present period to optimize WPC estimated value in forecast period acquisition, obtain a more accurate estimated value, and upgrade Error Gain.Here, the waiting Passengen number of described station subsequent period is predicted it is that iteration performs, predicts the waiting Passengen number of a following period repeatedly.
Thus, the waiting Passengen number of a station subsequent period is obtained.
In the above example, make use of Kalman filtering to predict the waiting Passengen number WPC of described station subsequent period.According to another embodiment of the invention, Bayesian filter also can be utilized to carry out described prediction.Bayesian filter is a kind of regressive filter based on probability density, and it carrys out the posterior probability density of tectonic system state variable with all Given informations.Except above-mentioned filtering method, those skilled in the art it will also be appreciated that the algorithm utilizing other similar is to carry out this prediction.
Figure 10 shows the KPI Key Performance Indicator KPI that utilization is arranged according to the waiting Passengen number of embodiments of the invention prediction.In the prior art, usually using passenger waiting time as KPI, and passenger waiting time was equal to for the 1/2 bus time interval simply.This traditional KPI only considers the operation of motorbus, does not but consider passenger.Such as, 100 passengers wait for 10 minutes from 5 passengers and wait for that the situation of 10 minutes is different, should reduce the stand-by period of most passenger as far as possible, thus improve the overall experience of service.Propose in the present invention and a kind of KPI towards passenger is set, that is, the passenger waiting time of weighting.Particularly, such as can using the waiting Passengen number predicted in the method for Fig. 4 and the integration of their stand-by period as KPI Key Performance Indicator KPI (the brick pattern part see in Figure 10).This is because just by method of the present invention, the waiting Passengen number of each period predicted can be obtained, thus described integration can be realized.
Figure 11 illustrates according to an embodiment of the invention for the process flow diagram of the evaluation method 1100 of the scheduling scheme of motorbus.Evaluation method 1100 comprises step 1110 to step 1140.Step 1110 in Figure 11 is identical with the process of 420 with the step 410 in Fig. 4 with 1120.
In step 1130, using prediction waiting Passengen number and the integration of their stand-by period as KPI Key Performance Indicator KPI.
In step 1140, the scheduling scheme of motorbus is evaluated, to determine whether that meeting described KPI Key Performance Indicator KPI is less than predetermined value.Such as, scheduling scheme can include but not limited to following means: notify driver's acceleration or deceleration of motorbus, the driver of notice motorbus jumps station, increase or reduce the departure interval or on platform, issue passenger's guidance information etc.The bus scheduling carried out after being provided with KPI can adopt various known method, is no longer described in detail at this, provides simple explanation by means of only an example.In one example in which, assuming that KPI=" passenger waiting time of weighting is less than 45 ".Now, carry out predicting and evaluating according to predicted value based on current scheduling scheme.Based on this evaluation, if KPI >=45 drawn, then can revise current scheduling scheme to produce new scheduling scheme, and again carry out predicting and evaluating based on new scheduling scheme, until find out the scheduling scheme meeting KPI<45.
Figure 12 shows the effect of the prediction according to waiting Passengen number of the present invention.The right side that the left side of Figure 12 shows actual WPC, the Figure 12 in certain day morning of station X shows the Contrast on effect of the method (not considering the position of motorbus) according to method of the present invention and prior art.As seen from the figure, the waiting Passengen number predicted of method according to the present invention and actual waiting Passengen number more close to and substantially identical.
Figure 13 illustrates according to an embodiment of the invention for waiting for the block scheme of system 1300 that ridership is predicted.This system 1300 comprises arrive at a station versus time estimator 1310 and waiting Passengen number fallout predictor 1320.Arrival time fallout predictor 1310 is configured to predict the arrival time that motorbus arrives a station based on the history running data of motorbus and Current vehicle service data.Waiting Passengen number fallout predictor 1320 is configured to based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, predicts the waiting Passengen number of described station subsequent period.
Figure 14 illustrates according to an embodiment of the invention for the block scheme of the evaluation system 1400 of the scheduling scheme of motorbus.Evaluation system 1400 comprises versus time estimator 1410 of arriving at a station, waiting Passengen number fallout predictor 1420, KPI Key Performance Indicator KPI arrange device 1430 and evaluator 1440.Arrival time fallout predictor 1410 is configured to predict the arrival time that motorbus arrives a station based on the history running data of motorbus and Current vehicle service data.Waiting Passengen number fallout predictor 1420 is configured to based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, predicts the waiting Passengen number of described station subsequent period.KPI Key Performance Indicator KPI arrange device 1430 be configured to using prediction waiting Passengen number and the integration of their stand-by period as KPI.Evaluator 1440 is configured to evaluate the scheduling scheme of motorbus, to determine whether that meeting described KPI Key Performance Indicator KPI is less than predetermined value.
The present invention can be system, method and/or computer program.Computer program can comprise computer-readable recording medium, containing the computer-readable program instructions for making processor realize various aspects of the present invention.
Computer-readable recording medium can be the tangible device that can keep and store the instruction used by instruction actuating equipment.Computer-readable recording medium can be such as the combination of--but being not limited to--storage device electric, magnetic storage apparatus, light storage device, electromagnetism memory device, semiconductor memory apparatus or above-mentioned any appropriate.The example more specifically (non exhaustive list) of computer-readable recording medium comprises: portable computer diskette, hard disk, random access memory (RAM), ROM (read-only memory) (ROM), erasable type programmable read only memory (EPROM or flash memory), static RAM (SRAM), Portable compressed dish ROM (read-only memory) (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, such as it stores punch card or the groove internal projection structure of instruction, and the combination of above-mentioned any appropriate.Here used computer-readable recording medium is not interpreted as momentary signal itself, the electromagnetic wave of such as radiowave or other Free propagations, the electromagnetic wave (such as, by the light pulse of fiber optic cables) propagated by waveguide or other transmission mediums or the electric signal by wire transfer.
Computer-readable program instructions as described herein can download to each calculating/treatment facility from computer-readable recording medium, or downloads to outer computer or External memory equipment by network, such as the Internet, LAN (Local Area Network), wide area network and/or wireless network.Network can comprise copper transmission cable, Optical Fiber Transmission, wireless transmission, router, fire wall, switch, gateway computer and/or Edge Server.Adapter in each calculating/treatment facility or network interface from network reception computer-readable program instructions, and forward this computer-readable program instructions, in the computer-readable recording medium be stored in each calculating/treatment facility.
The source code that the computer program instructions of the present invention's operation can be assembly instruction for performing, instruction set architecture (ISA) instruction, machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or the combination in any with one or more programming languages are write or object code, described programming language comprises OO programming language-such as Smalltalk, C++ etc., and the procedural programming languages of routine-such as " C " language or similar programming language.Computer-readable program instructions can fully perform on the user computer, partly perform on the user computer, as one, independently software package performs, partly part performs on the remote computer or performs on remote computer or server completely on the user computer.In the situation relating to remote computer, remote computer can by the network of any kind-comprise LAN (Local Area Network) (LAN) or wide area network (WAN)-be connected to subscriber computer, or, outer computer (such as utilizing ISP to pass through Internet connection) can be connected to.In certain embodiments, personalized customization electronic circuit is carried out by utilizing the status information of computer-readable program instructions, such as Programmable Logic Device, field programmable gate array (FPGA) or programmable logic array (PLA), this electronic circuit can perform computer-readable program instructions, thus realizes various aspects of the present invention.
Here various aspects of the present invention are described with reference to according to the process flow diagram of the method for the embodiment of the present invention, device (system) and computer program and/or block diagram.Should be appreciated that the combination of each square frame in each square frame of process flow diagram and/or block diagram and process flow diagram and/or block diagram, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to the processor of multi-purpose computer, special purpose computer or other programmable data treating apparatus, thus produce a kind of machine, make these instructions when the processor by computing machine or other programmable data treating apparatus performs, create the device of the function/action specified in the one or more square frames in realization flow figure and/or block diagram.Also these computer-readable program instructions can be stored in a computer-readable storage medium, these instructions make computing machine, programmable data treating apparatus and/or other equipment work in a specific way, thus, the computer-readable medium storing instruction then comprises a manufacture, and it comprises the instruction of the various aspects of the function/action specified in the one or more square frames in realization flow figure and/or block diagram.
Also can computer-readable program instructions be loaded on computing machine, other programmable data treating apparatus or miscellaneous equipment, make to perform sequence of operations step on computing machine, other programmable data treating apparatus or miscellaneous equipment, to produce computer implemented process, thus make function/action of specifying in the one or more square frames in the instruction realization flow figure that performs on computing machine, other programmable data treating apparatus or miscellaneous equipment and/or block diagram.
Process flow diagram in accompanying drawing and block diagram show system according to multiple embodiment of the present invention, the architectural framework in the cards of method and computer program product, function and operation.In this, each square frame in process flow diagram or block diagram can represent a part for a module, program segment or instruction, and a part for described module, program segment or instruction comprises one or more executable instruction for realizing the logic function specified.At some as in the realization of replacing, the function marked in square frame also can be different from occurring in sequence of marking in accompanying drawing.Such as, in fact two continuous print square frames can perform substantially concurrently, and they also can perform by contrary order sometimes, and this determines according to involved function.Also it should be noted that, the combination of the square frame in each square frame in block diagram and/or process flow diagram and block diagram and/or process flow diagram, can realize by the special hardware based system of the function put rules into practice or action, or can realize with the combination of specialized hardware and computer instruction.
Be described above various embodiments of the present invention, above-mentioned explanation is exemplary, and non-exclusive, and be also not limited to disclosed each embodiment.When not departing from the scope and spirit of illustrated each embodiment, many modifications and changes are all apparent for those skilled in the art.The selection of term used herein, is intended to explain best the principle of each embodiment, practical application or the technological improvement to the technology in market, or makes other those of ordinary skill of the art can understand each embodiment disclosed herein.
Claims (20)
1. the method for predicting wait ridership, comprising:
Based on the history running data of motorbus and Current vehicle service data, the arrival time that motorbus arrives a station is predicted; And
Based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, the waiting Passengen number of described station subsequent period is predicted.
2. method according to claim 1, wherein, history running data comprises at least one in the speed of the described motorbus corresponding to different time in one day in history, position.
3. method according to claim 1, wherein, Current vehicle service data comprises at least one in the current speed of described motorbus, position.
4. method according to claim 1, wherein, prediction is carried out to the waiting Passengen number of described station subsequent period and comprises, for described station:
Based on history passenger flow data, carry out the prediction arriving ridership;
Based on history passenger flow data, carry out the prediction of the vacant seat number of described motorbus;
Based on the predicting the outcome of described arrival time, predicting the outcome of described arrival ridership and predicting the outcome of described vacant seat number, carry out the prediction of stepping on car ridership; And
Based on described arrival ridership, described in step on car ridership and current waiting Passengen number, predict the waiting Passengen number of described station subsequent period.
5. method according to claim 4, wherein, the prediction arriving the prediction of ridership and the vacant seat number of described motorbus utilizes Seasonal Time Series Methods to perform.
6. method according to claim 4, wherein, in the prediction arriving ridership, the passenger climbing up same motorbus at same station is assumed to be and arrives this station according to specific distribution and the arriving at a station corresponding to a distribution of each motorbus, and the arrival ridership in the period equals the integration sum that is distributed in described in each in this period.
7. method according to claim 1, wherein, history passenger flow data comprise described station correspond in history different time in one day step in the vacant seat number of car ridership and described motorbus at least one.
8. method according to claim 1, wherein, current waiting Passengen number is taken by the video camera at described station and identifies.
9. method according to claim 4, the car ridership of stepping on also comprised based on prediction calculates and steps on the car time, and according to stepping on car time complexity curve motorbus and arrive the arrival time at next station.
10., for an evaluation method for the scheduling scheme of motorbus, comprising:
Based on the history running data of motorbus and Current vehicle service data, the arrival time that motorbus arrives a station is predicted;
Based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, the waiting Passengen number of described station subsequent period is predicted;
Using prediction waiting Passengen number and the integration of their stand-by period as KPI Key Performance Indicator KPI; And
The scheduling scheme of motorbus is evaluated, to determine whether described KPI Key Performance Indicator KPI is less than predetermined value.
11. 1 kinds, for the system predicted wait ridership, comprising:
Arrival time fallout predictor, is configured to predict the arrival time that motorbus arrives a station based on the history running data of motorbus and Current vehicle service data; And
Waiting Passengen number fallout predictor, is configured to based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, predicts the waiting Passengen number of described station subsequent period.
12. systems according to claim 11, wherein, history running data comprises at least one in the speed of the described motorbus corresponding to different time in one day in history, position.
13. systems according to claim 11, wherein, Current vehicle service data comprises at least one in the current speed of described motorbus, position.
14. systems according to claim 11, wherein, waiting Passengen number fallout predictor is also configured to for described station:
Based on history passenger flow data, carry out the prediction arriving ridership;
Based on history passenger flow data, carry out the prediction of the vacant seat number of described motorbus;
Based on the predicting the outcome of described arrival time, predicting the outcome of described arrival ridership and predicting the outcome of described vacant seat number, carry out the prediction of stepping on car ridership; And
Based on described arrival ridership, described in step on car ridership and current waiting Passengen number, predict the waiting Passengen number of described station subsequent period.
15. systems according to claim 14, wherein, the prediction arriving the prediction of ridership and the vacant seat number of described motorbus utilizes Seasonal Time Series Methods to perform.
16. systems according to claim 14, wherein, in the prediction arriving ridership, the passenger climbing up same motorbus at same station is assumed to be and arrives this station according to specific distribution and the arriving at a station corresponding to a distribution of each motorbus, and the arrival ridership in the period equals the integration sum that is distributed in described in each in this period.
17. systems according to claim 11, wherein, history passenger flow data comprise described station correspond in history different time in one day step in the vacant seat number of car ridership and described motorbus at least one.
18. systems according to claim 11, wherein, current waiting Passengen number is taken by the video camera at described station and identifies.
19. systems according to claim 14, wherein, waiting Passengen number fallout predictor is also configured to calculate step on the car time based on the car ridership of stepping on of prediction, and according to stepping on car time complexity curve motorbus and arrive the arrival time at next station.
20. 1 kinds, for the evaluation system of the scheduling scheme of motorbus, comprising:
Arrival time fallout predictor, is configured to predict the arrival time that motorbus arrives a station based on the history running data of motorbus and Current vehicle service data;
Waiting Passengen number fallout predictor, is configured based on history passenger flow data and current waiting Passengen number, and when considering the predicting the outcome of described arrival time, predicts the waiting Passengen number of described station subsequent period;
KPI Key Performance Indicator KPI arranges device, be configured to using prediction waiting Passengen number and the integration of their stand-by period as KPI; And
Evaluator, is configured to evaluate the scheduling scheme of motorbus, to determine whether described KPI Key Performance Indicator KPI is less than predetermined value.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410229206.1A CN105224992A (en) | 2014-05-28 | 2014-05-28 | To waiting for the method and system predicted of ridership and evaluation method and system |
| US14/722,879 US20150348068A1 (en) | 2014-05-28 | 2015-05-27 | Predicting waiting passenger count and evaluation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410229206.1A CN105224992A (en) | 2014-05-28 | 2014-05-28 | To waiting for the method and system predicted of ridership and evaluation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105224992A true CN105224992A (en) | 2016-01-06 |
Family
ID=54702284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410229206.1A Pending CN105224992A (en) | 2014-05-28 | 2014-05-28 | To waiting for the method and system predicted of ridership and evaluation method and system |
Country Status (2)
| Country | Link |
|---|---|
| US (1) | US20150348068A1 (en) |
| CN (1) | CN105224992A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106971246A (en) * | 2017-04-12 | 2017-07-21 | 青岛海信网络科技股份有限公司 | A kind of taxi Shang Ke areas passenger waiting time Forecasting Methodology and device |
| CN107274665A (en) * | 2017-07-31 | 2017-10-20 | 多维新创（北京）技术有限公司 | Bus transport capacity resource method and system for planning |
| CN107507413A (en) * | 2017-08-29 | 2017-12-22 | 广东蔚海数问大数据科技有限公司 | Vehicle location Forecasting Methodology and device |
| CN107545724A (en) * | 2017-07-05 | 2018-01-05 | 邹晓虎 | A kind of dynamic dispatching method of bus, device and system |
| CN108122424A (en) * | 2016-11-28 | 2018-06-05 | 高德信息技术有限公司 | Vehicle is in the definite method and apparatus of website berthing time |
| CN108877276A (en) * | 2018-08-31 | 2018-11-23 | 深圳市东部公共交通有限公司 | Quick predict bus travel time method, apparatus and terminal |
| CN108885718A (en) * | 2016-01-14 | 2018-11-23 | 摄取技术有限公司 | Localize time model prediction |
| CN109154507A (en) * | 2016-05-25 | 2019-01-04 | 福特全球技术公司 | Predict the point of interest waiting time for Estimated Time of Arrival |
| CN110211379A (en) * | 2019-05-27 | 2019-09-06 | 南京航空航天大学 | A kind of public transport method for optimizing scheduling based on machine learning |
| CN110946080A (en) * | 2018-09-27 | 2020-04-03 | 智能宠物家庭办公室公司 | System and method for coupling halves of a small animal habitat |
| CN111091196A (en) * | 2019-11-15 | 2020-05-01 | 佳都新太科技股份有限公司 | Passenger flow data determination method and device, computer equipment and storage medium |
| CN112001548A (en) * | 2020-08-25 | 2020-11-27 | 北京交通大学 | OD passenger flow prediction method based on deep learning |
| CN113516263A (en) * | 2021-04-21 | 2021-10-19 | 广州通巴达电气科技有限公司 | Vehicle scheduling method and device based on station image recognition |
| CN114202955A (en) * | 2021-12-30 | 2022-03-18 | 昆山市交通场站管理有限公司 | Bus station parking prediction method and parking prompt system |
| CN114299745A (en) * | 2021-12-30 | 2022-04-08 | 昆山市交通场站管理有限公司 | Parking space interaction system and method for bus and bus shelter |
| CN114943503A (en) * | 2021-02-17 | 2022-08-26 | 丰田自动车株式会社 | Operation management device, operation management system, and operation management method |
| CN116704778A (en) * | 2023-08-04 | 2023-09-05 | 创意(成都)数字科技有限公司 | Intelligent traffic data processing method, device, equipment and storage medium |
Families Citing this family (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10453020B2 (en) * | 2015-07-31 | 2019-10-22 | Nec Corporation | Method for providing a typical load profile of a vehicle for a public transport system |
| CN107180270A (en) * | 2016-03-12 | 2017-09-19 | 上海宏理信息科技有限公司 | Passenger flow forecasting and system |
| CN106056289B (en) * | 2016-06-06 | 2019-11-29 | 合肥天地软件科技有限公司 | A kind of bus service evaluation system based on cloud platform |
| US20180032964A1 (en) * | 2016-08-01 | 2018-02-01 | Nec Europe Ltd. | Transportation system and method for allocating frequencies of transit services therein |
| CN107798865B (en) * | 2016-09-07 | 2020-11-03 | 阿里巴巴（中国）有限公司 | Bus route running time estimation method and device |
| CN106897815B (en) * | 2017-01-17 | 2021-03-12 | 北京万相融通科技股份有限公司 | Method for predicting passenger flow trend of station in real time |
| CN107609608A (en) * | 2017-07-14 | 2018-01-19 | 上海丽界智能科技有限公司 | Clothes supervising device based on RFID label tag |
| CN109308539A (en) * | 2017-07-27 | 2019-02-05 | 上海宝信软件股份有限公司 | The method of passenger's retaining state of transfer stop in real-time estimation Metro Network |
| CN108622142A (en) * | 2018-03-30 | 2018-10-09 | 卡斯柯信号有限公司 | A kind of train intelligent operation adjustment system and method based on real-time passenger flow |
| CN108417038B (en) * | 2018-05-09 | 2021-02-09 | 华中科技大学鄂州工业技术研究院 | Method and system for predicting bus passenger flow |
| CN110570004A (en) * | 2018-06-05 | 2019-12-13 | 上海申通地铁集团有限公司 | subway passenger flow prediction method and system |
| CN109409563B (en) * | 2018-09-07 | 2021-11-09 | 北明软件有限公司 | Method, system and storage medium for analyzing real-time number of people in public transport operation vehicle |
| CN109558985A (en) * | 2018-12-10 | 2019-04-02 | 南通科技职业学院 | A kind of bus passenger flow amount prediction technique based on BP neural network |
| CN110837944A (en) * | 2019-08-27 | 2020-02-25 | 北京轨道交通路网管理有限公司 | Scheduling method, device and system |
| CN110533480A (en) * | 2019-09-04 | 2019-12-03 | 上海丙晟科技有限公司 | A kind of market passenger flow forecasting based on big data |
| CN110889092A (en) * | 2019-11-20 | 2020-03-17 | 北京市交通运行监测调度中心 | Short-time large-scale activity peripheral track station passenger flow volume prediction method based on track transaction data |
| CN111008747A (en) * | 2019-12-18 | 2020-04-14 | 贵州智诚科技有限公司 | Scenic spot passenger flow volume prediction method based on traffic data fusion |
| CN111667083B (en) * | 2020-06-11 | 2023-07-14 | 北京白龙马云行科技有限公司 | Method and device for determining estimated network taxi |
| CN111757272B (en) * | 2020-06-29 | 2024-03-05 | 北京百度网讯科技有限公司 | Prediction method, model training method and device for subway congestion degree |
| CN112133121B (en) * | 2020-09-23 | 2022-09-02 | 安徽蒂姆自动化科技有限公司 | Intelligent urban bus dispatching system |
| CN112562378B (en) * | 2020-12-01 | 2023-04-18 | 平安科技（深圳）有限公司 | Bus scheduling method and device, computer equipment and medium |
| CN113159377B (en) * | 2021-03-12 | 2024-03-12 | 江苏唱游数据技术有限公司 | Scenic spot smooth flow prediction model method based on multi-factor aggregation model |
| CN113159385A (en) * | 2021-03-22 | 2021-07-23 | 中铁信(北京)网络技术研究院有限公司 | Self-feedback passenger flow control method and device based on deep reinforcement learning |
| CN113239198B (en) * | 2021-05-17 | 2023-10-31 | 中南大学 | Subway passenger flow prediction method and device and computer storage medium |
| CN113658429B (en) * | 2021-08-11 | 2022-06-07 | 青岛海信网络科技股份有限公司 | Cooperative scheduling method and related device for bus corridor |
| CN114463054B (en) * | 2022-01-21 | 2023-07-18 | 浪潮卓数大数据产业发展有限公司 | Method and system for predicting park store passenger flow based on one-card communication |
| CN114693495B (en) * | 2022-05-24 | 2022-08-23 | 成都秦川物联网科技股份有限公司 | Smart city public traffic management method, Internet of things system, device and medium |
| CN115358645B (en) * | 2022-10-21 | 2023-01-17 | 安徽中科中涣信息技术有限公司 | Bus passenger flow monitoring and dispatching management terminal |
| TWI848475B (en) * | 2022-12-16 | 2024-07-11 | 鴻海精密工業股份有限公司 | Method for determining recommended number of waiting passengers, electronic device, and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5035302A (en) * | 1989-03-03 | 1991-07-30 | Otis Elevator Company | "Artificial Intelligence" based learning system predicting "Peak-Period" times for elevator dispatching |
| GB2294114A (en) * | 1994-10-10 | 1996-04-17 | Lg Ind Systems Co Ltd | System for counting the number of people waiting for a lift |
| US6374176B1 (en) * | 1996-08-13 | 2002-04-16 | Nextbus Information Systems, Inc. | Public transit vehicle arrival information system |
| US20030208313A1 (en) * | 2002-05-01 | 2003-11-06 | Wells Charles Hilliary | System for computing speeds and estimated arrival times for moving vehicles |
| CN102157075A (en) * | 2011-03-15 | 2011-08-17 | 上海交通大学 | Method for predicting bus arrivals |
| CN102708701A (en) * | 2012-05-18 | 2012-10-03 | 中国科学院信息工程研究所 | System and method for predicting arrival time of buses in real time |
| CN203376873U (en) * | 2013-06-06 | 2014-01-01 | 开平市中铝实业有限公司 | Bus arrival forecasting system |
-
2014
- 2014-05-28 CN CN201410229206.1A patent/CN105224992A/en active Pending
-
2015
- 2015-05-27 US US14/722,879 patent/US20150348068A1/en not_active Abandoned
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5035302A (en) * | 1989-03-03 | 1991-07-30 | Otis Elevator Company | "Artificial Intelligence" based learning system predicting "Peak-Period" times for elevator dispatching |
| GB2294114A (en) * | 1994-10-10 | 1996-04-17 | Lg Ind Systems Co Ltd | System for counting the number of people waiting for a lift |
| US6374176B1 (en) * | 1996-08-13 | 2002-04-16 | Nextbus Information Systems, Inc. | Public transit vehicle arrival information system |
| US20030208313A1 (en) * | 2002-05-01 | 2003-11-06 | Wells Charles Hilliary | System for computing speeds and estimated arrival times for moving vehicles |
| CN102157075A (en) * | 2011-03-15 | 2011-08-17 | 上海交通大学 | Method for predicting bus arrivals |
| CN102708701A (en) * | 2012-05-18 | 2012-10-03 | 中国科学院信息工程研究所 | System and method for predicting arrival time of buses in real time |
| CN203376873U (en) * | 2013-06-06 | 2014-01-01 | 开平市中铝实业有限公司 | Bus arrival forecasting system |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108885718A (en) * | 2016-01-14 | 2018-11-23 | 摄取技术有限公司 | Localize time model prediction |
| US12067501B2 (en) | 2016-01-14 | 2024-08-20 | Uptake Technologies, Inc. | Localized temporal model forecasting |
| CN109154507A (en) * | 2016-05-25 | 2019-01-04 | 福特全球技术公司 | Predict the point of interest waiting time for Estimated Time of Arrival |
| CN109154507B (en) * | 2016-05-25 | 2023-04-14 | 福特全球技术公司 | Predicting point of interest latency for estimated arrival times |
| CN108122424B (en) * | 2016-11-28 | 2020-04-14 | 高德信息技术有限公司 | Method and device for determining stop time of vehicle at station |
| CN108122424A (en) * | 2016-11-28 | 2018-06-05 | 高德信息技术有限公司 | Vehicle is in the definite method and apparatus of website berthing time |
| CN106971246A (en) * | 2017-04-12 | 2017-07-21 | 青岛海信网络科技股份有限公司 | A kind of taxi Shang Ke areas passenger waiting time Forecasting Methodology and device |
| CN107545724A (en) * | 2017-07-05 | 2018-01-05 | 邹晓虎 | A kind of dynamic dispatching method of bus, device and system |
| CN107274665A (en) * | 2017-07-31 | 2017-10-20 | 多维新创（北京）技术有限公司 | Bus transport capacity resource method and system for planning |
| CN107507413A (en) * | 2017-08-29 | 2017-12-22 | 广东蔚海数问大数据科技有限公司 | Vehicle location Forecasting Methodology and device |
| CN108877276A (en) * | 2018-08-31 | 2018-11-23 | 深圳市东部公共交通有限公司 | Quick predict bus travel time method, apparatus and terminal |
| CN110946080A (en) * | 2018-09-27 | 2020-04-03 | 智能宠物家庭办公室公司 | System and method for coupling halves of a small animal habitat |
| CN110211379A (en) * | 2019-05-27 | 2019-09-06 | 南京航空航天大学 | A kind of public transport method for optimizing scheduling based on machine learning |
| CN111091196A (en) * | 2019-11-15 | 2020-05-01 | 佳都新太科技股份有限公司 | Passenger flow data determination method and device, computer equipment and storage medium |
| CN111091196B (en) * | 2019-11-15 | 2022-08-02 | 佳都科技集团股份有限公司 | Passenger flow data determination method and device, computer equipment and storage medium |
| CN112001548A (en) * | 2020-08-25 | 2020-11-27 | 北京交通大学 | OD passenger flow prediction method based on deep learning |
| CN112001548B (en) * | 2020-08-25 | 2023-10-20 | 北京交通大学 | OD passenger flow prediction method based on deep learning |
| CN114943503A (en) * | 2021-02-17 | 2022-08-26 | 丰田自动车株式会社 | Operation management device, operation management system, and operation management method |
| CN113516263A (en) * | 2021-04-21 | 2021-10-19 | 广州通巴达电气科技有限公司 | Vehicle scheduling method and device based on station image recognition |
| CN114202955A (en) * | 2021-12-30 | 2022-03-18 | 昆山市交通场站管理有限公司 | Bus station parking prediction method and parking prompt system |
| CN114299745A (en) * | 2021-12-30 | 2022-04-08 | 昆山市交通场站管理有限公司 | Parking space interaction system and method for bus and bus shelter |
| CN116704778A (en) * | 2023-08-04 | 2023-09-05 | 创意(成都)数字科技有限公司 | Intelligent traffic data processing method, device, equipment and storage medium |
| CN116704778B (en) * | 2023-08-04 | 2023-10-24 | 创意(成都)数字科技有限公司 | Intelligent traffic data processing method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| US20150348068A1 (en) | 2015-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105224992A (en) | To waiting for the method and system predicted of ridership and evaluation method and system | |
| Iglesias et al. | Data-driven model predictive control of autonomous mobility-on-demand systems | |
| US20220248171A1 (en) | System and Methods for Automatically Checking-In a Vehicle | |
| CN110998568B (en) | Navigation determination system and method for embarkable vehicle seeking passengers | |
| Nourinejad et al. | A dynamic carsharing decision support system | |
| US10019671B2 (en) | Learning mobility user choice and demand models from public transport fare collection data | |
| Chen et al. | Uncertainty in urban mobility: Predicting waiting times for shared bicycles and parking lots | |
| US10430736B2 (en) | System and method for estimating a dynamic origin-destination matrix | |
| US20200364627A1 (en) | System and method for ride order dispatching | |
| CN109409626A (en) | For the scheduling of airline operational and the Accumulation Model of resource allocation | |
| CN111033535A (en) | System and method for bus order scheduling | |
| JP6675860B2 (en) | Data processing method and data processing system | |
| JP6906487B2 (en) | Demand forecasting device for shared vehicles, demand forecasting method and program for shared vehicles | |
| US20190095836A1 (en) | Prediction of actual loads from fare collection data | |
| CN110458325A (en) | A kind of traffic zone passenger flow forecasting and device in short-term | |
| CN114692419A (en) | Digital twin modeling method and system for urban rail transit system | |
| CN115170006B (en) | Dispatching method, device, equipment and storage medium | |
| CN115049152A (en) | Airport transfer area arrival passenger flow prediction method and device and electronic equipment | |
| Noursalehi et al. | Predictive decision support platform and its application in crowding prediction and passenger information generation | |
| CN114372830A (en) | Network taxi booking demand prediction method based on space-time multi-graph neural network | |
| CN116324838A (en) | System and method for scheduling shared rides through a taxi calling platform | |
| Nguyen et al. | Pareto routing and scheduling of dynamic urban rail transit services with multi-objective cross entropy method | |
| US12061090B2 (en) | Vehicle repositioning on mobility-on-demand platforms | |
| La Rocca et al. | Heuristics for electric taxi fleet management at Teo Taxi | |
| CN115983896A (en) | Demand forecasting method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160106 |